motimalu
Flat Color - Style
Trained on images without visible lineart and flat colors and little to no indication of depth.
This is another small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular.
Recommended prompt structure:
Positive prompt:
flat color, no lineart,
{{tags}}
masterpiece, best quality, very awa, absurdresNegative prompt:
(worst quality, low quality, sketch:1.1), error, bad anatomy, bad hands, watermark, ugly, distorted, censored, lowres, abstract, signature, bkubPopularity
Info
Version v2.0 [noobai-v-pred-1]: 1 File
About this version: v2.0 [noobai-v-pred-1]
v2 changelog:
- large dataset update to better target flat color and no lineart styles and techniques, including blending
Trained on NoobAI-XL (NAI-XL) V-Pred 1.0-Version
With the kohya_ss dev branch, v_paratemization ,zero_terminal_ssr enabled, and noise offet set to 0.
Previews are generated in Forge with DynamicThresholding (CFG-Fix) Integrated enabled, settings:
dynthres_enabled: True, dynthres_mimic_scale: 5, dynthres_threshold_percentile: 1, dynthres_mimic_mode: Half Cosine Down, dynthres_mimic_scale_min: 1, dynthres_cfg_mode: Half Cosine Down, dynthres_cfg_scale_min: 3, dynthres_sched_val: 1, dynthres_separate_feature_channels: enable, dynthres_scaling_startpoint: ZERO, dynthres_variability_measure: STD, dynthres_interpolate_phi: 1A ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095
14 Versions
Go ahead and upload yours!
